Qlarify Labs
Evals
How we evaluate AI systems to find their limits. Each entry is a repeatable testing technique — the durable knowledge, independent of any one model or version.
Qlarify Labs
How we evaluate AI systems to find their limits. Each entry is a repeatable testing technique — the durable knowledge, independent of any one model or version.
6 methods
Deliberately craft inputs designed to elicit failure — confusion, unsafe output, or broken constraints — to map the model's weak boundaries.
Route a small slice of real traffic to a new model or prompt first, watch it closely, and widen or roll back based on what the canary shows.
Probe whether a deployed model can be cheaply queried to reconstruct its behaviour, training data, or a usable distilled copy — a confidentiality and IP attack surface.
Feed anomalous tokens, rare unicode, homoglyphs and malformed encodings to trigger out-of-distribution behavior.
Treat the safety filters around the model as their own system under test — measuring bypass rate on unsafe inputs, false-positive cost on benign ones, and what happens when the guardrail itself fails.
Embed adversarial instructions in user input or retrieved/tool content to test whether the model follows attacker text over its system policy.